Jana Kolassa

Soil Moisture Retrieval Using Neural Networks: Application to SMOS

A methodology to retrieve soil moisture (SM) from Soil Moisture and Ocean Salinity (SMOS) data is presented. The method uses a neural network (NN) to find the statistical relationship linking the input data to a reference SM data set. The input data are composed of passive microwaves (L-band SMOS brightness temperatures,

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): a statistically based estimate of global surface turbulent fluxes and gross primary productivity using solar-induced fluorescence

T_{b}

Soil moisture retrieval from SMOS observations using neural networks

s) complemented with active microwaves (C-band Advanced Scatterometer (ASCAT) backscattering coefficients), and Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) . The reference SM data used to train the NN are the European Centre For Medium-Range Weather Forecasts model predictions. The best configuration of SMOS data to retrieve SM using an NN is using

Estimating surface soil moisture from SMAP observations using a Neural Network technique

T_{b}

Statistical retrieval of surface and root zone soil moisture using synergy of multi-frequency remotely-sensed observations

s measured with both H and V polarizations for incidence angles from 25° to 60°. The inversion of SM can be improved by ~10% by adding MODIS NDVI and ASCAT backscattering data and by an additional ~5% by using local information on the maximum and minimum records of SMOS Tbs (or ASCAT backscattering coefficients) and the associated SM values. The NN-inverted SM is able to capture the temporal and spatial variability of the SM reference data set. The temporal variability is better captured when either adding active microwaves or using a local normalization of SMOS Tbs. The NN SM products have been evaluated against in situ measurements, giving results of comparable or better (for some NN configurations) quality to other SM products. The NN used in this paper allows to retrieve SM globally on a daily basis. These results open interesting perspectives such as a near-real-time processor and data assimilation in weather prediction models.

Statistical downscaling of remotely-sensed soil moisture

A new global estimate of surface turbulent fluxes, latent heat flux (LE) and sensible heat flux (H), and gross primary production (GPP) is developed using a machine learning approach informed by novel remotely sensed Solar-Induced Fluorescence (SIF) and other radiative and meteorological variables. This is the first study to jointly retrieve LE, H and GPP using SIF observations. The approach uses an artificial neural network (ANN) with a target dataset generated from three independent data sources, weighted based on triple collocation (TC) algorithm. The new retrieval, named Water, Energy, and Carbon with Artificial Neural Networks (WECANN), provides estimates of LE, H and GPP from 2007 to 2015 at 1° × 1° spatial resolution and on monthly time resolution. The quality of ANN training is assessed using the target data, and the WECANN retrievals are evaluated using eddy covariance tower estimates from FLUXNET network across various climates and conditions. When compared to eddy covariance estimates, WECANN typically outperforms other products, particularly for sensible and latent heat fluxes. Analysing WECANN retrievals across three extreme drought and heatwave events demonstrates the capability of the retrievals in capturing the extent of these events. Uncertainty estimates of the retrievals are analysed and the inter-annual variability in average global and regional fluxes show the impact of distinct climatic events - such as the 2015 El Niño - on surface turbulent fluxes and GPP.

Soil moisture retrieval from multi‐instrument observations: Information content analysis and retrieval methodology

A methodology to retrieve soil moisture (SM) from multiinstrument remote sensing data is presented. The method uses a Neural Network (NN) to find the statistical relationship linking the input data to a reference SM dataset. The input data is composed of passive microwaves (L-band SMOS brightness temperatures), active microwaves (C-band ASCAT backscattering coefficients), and visible and infrared observations by MODIS. The reference SM data used to train the NN are ECMWF model predictions or SMOS L3 SM. After determining the best configuration of input data to retrieve SM using a NN, the NN soil moisture product is evaluated with respect to other global SM products and with respect to in situ measurements. The NN is able to capture the spatial and temporal dynamics of SM, and the SM computed with NNs compares well with the other SM datasets.

Regionally strong feedbacks between the atmosphere and terrestrial biosphere

A Neural Network (NN) algorithm was developed to estimate global surface soil moisture for April 2015 to March 2017 with a 2-3 day repeat frequency using passive microwave observations from the Soil Moisture Active Passive (SMAP) satellite, surface soil temperatures from the NASA Goddard Earth Observing System Model version 5 (GEOS-5) land modeling system, and Moderate Resolution Imaging Spectroradiometer-based vegetation water content. The NN was trained on GEOS-5 soil moisture target data, making the NN estimates consistent with the GEOS-5 climatology, such that they may ultimately be assimilated into this model without further bias correction. Evaluated against in situ soil moisture measurements, the average unbiased root mean square error (ubRMSE), correlation and anomaly correlation of the NN retrievals were 0.037 m3m-3, 0.70 and 0.66, respectively, against SMAP core validation site measurements and 0.026 m3m-3, 0.58 and 0.48, respectively, against International Soil Moisture Network (ISMN) measurements. At the core validation sites, the NN retrievals have a significantly higher skill than the GEOS-5 model estimates and a slightly lower correlation skill than the SMAP Level-2 Passive (L2P) product. The feasibility of the NN method was reflected by a lower ubRMSE compared to the L2P retrievals as well as a higher skill when ancillary parameters in physically-based retrievals were uncertain. Against ISMN measurements, the skill of the two retrieval products was more comparable. A triple collocation analysis against Advanced Microwave Scanning Radiometer 2 (AMSR2) and Advanced Scatterometer (ASCAT) soil moisture retrievals showed that the NN and L2P retrieval errors have a similar spatial distribution, but the NN retrieval errors are generally lower in densely vegetated regions and transition zones.

A joint analysis of modeled soil moisture fields and satellite observations

Plants photosynthetic activity and transpiration are constrained by the amount of water available to them through roots (i.e. root zone soil moisture) as well as nutrient and atmospheric conditions. Therefore, to better understand the response of plants to different stress conditions, knowledge of root zone soil moisture is essential. However, current global satellites dedicated to soil moisture monitoring are limited to L-band frequencies that have a low (< 5cm) penetration depth. In this study, we implement a new root zone soil moisture retrieval algorithm that takes advantage of multi-frequency microwave observations to infer root soil moisture from L-band measurements and inspired by plant hydraulics. The algorithm is a statistical retrieval that uses a set of target data to train an artificial neural network. Results of applying the retrieval algorithm to one year of observations along with future validation measures is presented.

Water, Energy, and Carbon with Artificial Neural Networks (WECANN): A statistically-based estimate of global surface turbulent fluxes using solar-induced fluorescence

Global soil moisture estimates at fine spatial resolutions is necessary for many applications. However, current spaceborne instruments have coarse resolution. In this study, we develop a new Artificial Neural Network (ANN) based disaggregation algorithm to downscale soil moisture observations from Soil Moisture Active Passive (SMAP) mission to a fine resolution of ∼2km using ancillary data from visible/infrared frequencies. We use soil moisture estimates from SMAP at two different spatial resolutions to train the downscaling algorithm. Results show that ANN can successfully capture the complex relationship between the soil moisture estimates at two different spatial resolutions using the ancillary data provided.